vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add qwen2moe (#6074)

Browse source 
* support qwen2moe

* fix-review

* metal : support unary ops for nelements % 4 != 0

* metal : require contiguousness for float4 unary kernels

* metal : require contiguousness for float4 unary kernels (cont)

* fix-review

* names : for brevity "SHARED_EXP" -> "SHEXP"

* llama : reuse build_moe_ffn()

* llama : add model type name

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Shijie 2024-04-16 23:40:48 +08:00 • committed by GitHub
parent 8a56075b07
commit f4dea7da18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 537 additions and 101 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tests/test-backend-ops.cpp
View file

@ -1878,6 +1878,7 @@ static bool test_backend(ggml_backend_t backend, test_mode mode, const char * op
// unary ops
for (int op = 0; op < GGML_UNARY_OP_COUNT; op++) {
test_cases.emplace_back(new test_unary((ggml_unary_op) op));
test_cases.emplace_back(new test_unary((ggml_unary_op) op, GGML_TYPE_F32, { 7, 13, 19, 23 }));
}
test_cases.emplace_back(new test_get_rows(GGML_TYPE_F32, 1, 8, 2, 1, false));